Autoregressive Score Matching
Authors: Chenlin Meng, Lantao Yu, Yang Song, Jiaming Song, Stefano Ermon
NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We show with extensive experimental results that it can be applied to density estimation on synthetic data, image generation, image denoising, and training latent variable models with implicit encoders. |
| Researcher Affiliation | Academia | Chenlin Meng Stanford University chenlin@stanford.edu Lantao Yu Stanford University lantao@cs.stanford.edu Yang Song Stanford University yangsong@cs.stanford.edu Jiaming Song Stanford University tsong@cs.stanford.edu Stefano Ermon Stanford University ermon@cs.stanford.edu |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide an explicit statement or link for open-source code for the described methodology. |
| Open Datasets | Yes | We then perform density estimation on 2-d synthetic datasets (see Appendix B) and three commonly used image datasets: MNIST, CIFAR-10 [12] and Celeb A [13]. ... We use SVHN, constant uniform and uniform as OOD distributions following [3]. |
| Dataset Splits | No | The paper mentions using datasets like MNIST, CIFAR-10, and Celeb A, and refers to a "test set" for CIFAR-10, but does not provide specific numerical percentages or counts for training, validation, and test splits, nor does it cite the exact split methodologies used for these datasets. |
| Hardware Specification | Yes | Moreover, the memory required grows rapidly w.r.t the data dimension, which triggers memory error on 12 GB TITAN Xp GPU when the data dimension is approximately 200. |
| Software Dependencies | No | The paper mentions the use of existing models like Pixel CNN++ and MADE but does not specify any software libraries, frameworks, or their version numbers that were used for implementation or experimentation. |
| Experiment Setup | No | The paper describes general architectural choices (e.g., "fully connected network with 3 hidden layers", "MADE model") and mentions that additional details can be found in appendices, but it does not provide concrete hyperparameter values (e.g., learning rates, batch sizes, number of epochs) in the main text. |